Gianluca Mazza PRO

You're right, and thanks for running it against the wheel. After a recall, every new turn is encoded on the mood engine first and gated just imports it, so the leak always lands in gated, including when the recall ran in gated mode. Both of your mechanisms hold: the reverse links that encode() writes stay on the mood side, and the tag is built from the mood engine's state. Two more fields go the same way: momentum, and the strengths of the new memory's forward links, which are scored against the mood store. core_affect doesn't leak. Our turns were different from yours, so our values are too, but the pattern is the same: gated's new tags equal mood's, and gated's running state equals the reference.

We see two things differently. First, in our runs the snapshot doesn't outweigh the links. Repairing only the links or only the tags left a similar number of top-3 changes: in a small store the margins are tiny, so even a weak s6 can flip an order. Second, "Compare both modes" is fair between its two arms, because both copies come from one engine. But with the radio on "Query-gated", that engine is the gated one, so before the fix Compare was reading the leaky store.

On the ids: no. The import was there to keep one appraisal per turn and to stop recall write-backs from crossing over. Matching ids were a side effect, and the missing back-links and the state copied over from the mood engine were an oversight on our side. Nothing in the demo depends on matching ids.

Your swap is now live on the Space. After a recall, gated encodes each new turn itself, with the same appraisal (gated.encode(content, appraisal=memory.tag.appraisal)), and the separate observe is gone, so its state doesn't advance twice. A new test checks tags, back-links and state against a fresh engine fed the same turns, with the recall in either mode. It's a demo-only change, and the fix is yours, so thank you.

Thanks, this is a fair catch and mostly right. Two corrections: reconsolidation pulls the tag toward the running core affect, not the mood, and co-retrieval only strengthens links that already exist; it never adds new ones. Two more points. The cosine-only branch ranks independently of earlier writes, but it still writes to its own top 3. And once a memory's window is open, any recall within the next 5 minutes reconsolidates it again, whatever the prediction error, which is exactly your A-then-B case.

There's also a bigger factor you didn't mention. After each recall the demo appraises its own reply, and that can shift the affective state before the next recall. So copying the store alone wouldn't make the comparison fair; the state has to be snapshotted too.

The write-backs are intended: they're the mechanism the demo is there to show, and they're documented. What wasn't fair was reading the toggle as a comparison, because the write-backs skew it. So each mode now keeps its own memory and state: normal recall still writes, but only to the memory of the mode you used, so it no longer changes what the other mode sees. A new "Compare both modes" button runs both modes on scratch copies of the same snapshot, without changing your session. There's also a line in the demo that explains the write-backs.

I've added a toggle to the Space so you can compare the state-based and query-gated paths side by side.

Thanks, you're right on the substance.

The Space runs live LLM appraisal, so affect is inferred, not given. That's the setting where my own pre-registered results show no advantage over plain cosine, and the card says so under "Scope and limits". The Addendum P numbers you quoted are correct (0.887 vs 0.800 top-1). But P used a different model and embedder, with queries answerable from text alone, so it tells you about this kind of setting, not about the demo itself.

You're also right about recall: it calls retrieve() without query_affect, so the mood term scores against the running conversation state. That's the "current mood" behaviour the UI describes. retrieve_query_gated() ships in 0.18.1. Addendum Y's +0.076 over the always-on query-appraised arm is correct, but on ES-MemEval the gated path still doesn't beat plain cosine. The demo predates the gate and I haven't switched it since; it's there to show the mechanism, not the best retrieval setup.

Agreed: the hit list is what the answer actually saw, so it belongs in the receipt next to the query and the index revision. To be clear about today: RAGFS prints results to stdout with no stable hit id, no rank, no stored receipt and no index revision, so that replay check can't be run on it. A top-k mismatch would also be a retrieval-eval gap, not an undo problem: undo in RAGFS is the documented soft-delete reverse for file operations, and it doesn't fix a wrong hit.

Agreed, and the revision pin is the part I'd underline. A receipt without the index revision tells you what was asked, not what it was asked against. Today RAGFS prints the query JSON, but storing it beside the answer with the index revision is up to the caller. Making that pairing explicit would be a good next step.